CNN-based 3D thermal modeling of the soil for antipersonnel mine detection

Abstract

The inherent analogies between the defining equation of CNN and that of heat transfer are well known. In this paper, we explore the projection of a 3D thermal model of the soil on this kind of structure. In so doing, reliable and fast prediction of the thermodynamic behavior of soil subject to known boundary conditions can be obtained. That way, it is possible to characterize different kinds of soil in terms of its thermal signature. Based on that knowledge, and using an inverse approach, we perform the detection of buried land mines.